Sciatlas Literature Review

What it does

When your agent uses it

• The user asks for a literature review
• Related work section
• Topic overview grounded in the provided SciAtlas paper backend

Example prompts

• “/sciatlas-literature-review”

Requirements

• Python 3
• A credential in SCIATLAS_API_KEY
• A credential in OPENAI_API_KEY

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1This dedicated workflow requires a full SciAtlas checkout. If it is missing, clone the repository, change into it, then run python -m pip…
2. 2Check current environment and .env for SCIATLAS_API_KEY and LLM settings before asking the user.
3. 3If no SciAtlas token is configured, guide the user to http://sciatlas.openkg.cn/register; ask for email, verification code, and returned…
4. 4If LLM credentials are required and missing, ask only for the missing values. Use the user's provider values without printing them back.
5. 5Configure the current shell or .env yourself, then run the workflow.

What it can do on your machine

Read from SKILL.md and the folder at commit e8873a9. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • sciatlas.openkg.cn
  • api.deepseek.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • SCIATLAS_API_KEY
  • DMX_API_KEY
  • LLM_API_KEY
  • SEARCH_LLM_API_KEY
  • OPENAI_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sciatlas Literature Review loads about 1.7k tokens when it runs. Until then it costs about 134 tokens; SKILL.md has 669 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~134

When it runs · the whole SKILL.md, loaded when a task matches

~1.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:13

  the CLI, guide registration, configure `.env` or shell variables, run the workflow, inspect artifacts, and synthesize t

• NoteMentions a .env fileSKILL.md:32

  3. Check current environment and `.env` for `SCIATLAS_API_KEY` and LLM settings before asking the user.

• NoteMentions a .env fileSKILL.md:35

  6. Configure the current shell or `.env` yourself, then run the workflow.

• NoteMentions a .env fileSKILL.md:39

  Configure workflow credentials in `.env` or the shell:

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from zjunlp/SciAtlas at commit e8873a9, republished under its MIT licence (© zjunlp). 669 words, ~1,661 tokens.

name

sciatlas-literature-review

description

Use only the current SciAtlas literature-review workflow (`literature_review_pipeline`) to take a novice user from zero setup to a final evidence-grounded survey outline, paper map, or literature review, including setup, registration guidance, workflow configuration, SciAtlas backend retrieval, artifact reading, and synthesis. Trigger when the user asks for a literature review, related work section, paper map, survey outline, reading path, or topic overview grounded in the provided SciAtlas paper backend.

python run_sciatlas.py literature-review -h

SCIATLAS_API_BASE_URL=http://sciatlas.openkg.cn
SCIATLAS_API_KEY=<sciatlas-token>
OPENAI_API_KEY=<llm-key>
OPENAI_BASE_URL=https://api.deepseek.com
LLM_MODEL=deepseek-v4-flash

python run_sciatlas.py literature-review \
  --query "<topic>" \
  --domain "<optional field>" \
  --workflow flash

python run_sciatlas.py literature-review \
  --query "<topic>" \
  --domain "<optional field>" \
  --workflow full

python run_sciatlas.py literature-review \
  --query "<topic>" \
  --domain "<optional field>" \
  --workflow flash \
  --probe-top-k 3 \
  --round-top-k 3 \
  --round1-action-limit 1 \
  --llm-paper-limit 12 \
  --report-stop-after packs \
  --workflow-timeout 600 \
  --llm-timeout 120 \
  --outline-timeout 180

© zjunlp, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in agent-skill/sciatlas-literature-review of zjunlp/SciAtlas.

• SKILL.md
• agents/openai.yaml

Open the folder on GitHubat commit e8873a9